Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Channel recommendation method based on individual history and current behavior fusion of group

A technology for recommending methods and channels, applied in the IPTV field, can solve the problems of little discovery, a lot of time-consuming, etc., and achieve the effect of easy acquisition and saving computing resources.

Active Publication Date: 2018-08-17
SOUTH CHINA UNIV OF TECH
View PDF14 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods either require additional user rating information, or require a large amount of time-consuming machine calculations. At present, there are still few effective recommendation algorithms directly targeting live channels.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Channel recommendation method based on individual history and current behavior fusion of group
  • Channel recommendation method based on individual history and current behavior fusion of group
  • Channel recommendation method based on individual history and current behavior fusion of group

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] A channel recommendation method based on the fusion of individual history and group current behavior, such as figure 1 ,include:

[0043] For overall users, design a current channel state matrix generator (101), be used to describe the current state of each channel when the user watches IPTV; For individual users, design a personalized historical state matrix generator (102), for Describe each user within a certain historical time, the state of each historical viewing channel, and send the current channel state matrix constructed by 101 and the personalized historical state matrix constructed by 102 into the user recommendation computing module (103), which The recommendation algorithm used by the module can generate a recommended program list for each user, and send it to the push module (104) to push independently for the user.

[0044] One, for the construction of current channel state matrix generator (101), comprise the following steps:

[0045] 1. Select the tim...

Embodiment 2

[0071] A real-time channel recommendation strategy based on intersection selection method, figure 2 An example of using the intersection selection method to carry out real-time channel recommendation for IPTV users is described. In this example, the recommendation by the intersection selection method includes the following steps:

[0072] 1) Select the time window Δt, and count the number of viewers p of each channel within the time window [t-Δt,t) i .

[0073] 2) Calculate the growth rate of the number of online users of each channel within the time window [t-Δt,t)

[0074]

[0075] 3) to p i and r i For normalization, P i for p i The normalized value, R i for r i Normalized value. Construct the current channel state matrix at time t Each row of the matrix represents the channel C in the time window [t-Δt,t) i The number of viewers, the growth rate of the number of viewers online;

[0076] 4) For user U, build the user’s personal historical viewing chann...

Embodiment 3

[0082] A real-time channel recommendation strategy based on distance selection method, Figure 4 An example of using the distance selection method to perform real-time channel recommendation for IPTV users is described. The recommendation by the distance selection method includes the following steps:

[0083] Step 1: Calculate the distance between each row vector in matrix C and each row vector in matrix H. The row vector does not include the channel number. The distance can be calculated in various ways. This example uses Euclidean distance as an example, such as matrix Row vector vec in C 1 =(P 1 , R 1 ) and the row vector vec in matrix H 2 =(O 1 ,W 1 ) is calculated as follows:

[0084] Here P 1 Indicates channel C in matrix C 1 of viewers, O 1 Represents channel C in matrix H 1 of views, R 1 Indicates channel C in matrix C 1 growth rate, W 1 Represents channel C in matrix H 1 the weight of. By extension, Here P i Indicates channel C in matrix C i of vi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a channel recommendation method based on individual history and current behavior fusion of a group. The method comprises the steps of firstly, constructing a current viewed channel state matrix of the group for describing the characteristics of each current channel, the characteristics including the current number of viewers of each channel and the on-line viewer growth rate of each channel; then constructing an individual historical viewed channel state matrix for an individual user for describing the viewed channel characteristics of the user within the past period oftime, including the frequency that the user viewed each channel and the weight of each viewed channel; and finally, sending the current channel state matrix of the group and the individual historicalviewed channel state matrix to a recommendation fusion calculation module, calculating channels that each user may view at the current moment by using an intersection selection method or a distance selection method, and pushing N channels that are viewed most possibly to the user.

Description

technical field [0001] The invention relates to the field of IPTV, in particular to a channel recommendation method based on the integration of individual history and group current behavior. Background technique [0002] IPTV is an interactive Internet TV, and the TV channel recommendation based on IPTV has an attractive application prospect. With the development of IPTV and Internet TV live broadcast technology, users can watch more and more TV channels, so the traditional TV program guide (EPG) can no longer meet the needs of people to find the channels they are interested in in time. In recent years, people have begun to study personalized recommendation systems for IPTV. However, most recommendation systems are only for on-demand programs rather than live recommendations, because the following characteristics of live channels make it more complicated to recommend: [0003] Timeliness: Live TV content will only be played within a specific time window. If users want to wa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04N21/466H04N21/442H04N21/45H04N21/482
CPCH04N21/442H04N21/44213H04N21/4532H04N21/4668H04N21/4826
Inventor 杨灿任思璇徐映雪盛栋铭
Owner SOUTH CHINA UNIV OF TECH
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com